Neural Electromagnetic Simulation Training with Time-reversal Consistency

Neural Electromagnetic Simulation Training with Time-reversal Consistency | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Neural Electromagnetic Simulation Training with Time-reversal Consistency Shrija Nayanan, Vikram Chopra, Priya Sharma, Aarav Patel This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4870131/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Conventional electromagnetic wave simulators are characterized by lengthy simulation times, making them unsuitable for computational imaging and photonic inverse problems (such as end-to-end design and iterative reconstruction) that necessitate multiple evaluations of the forward model. Neural network-based electromagnetic wave simulators offer potential speed improvements by several orders of magnitude; however, traditional supervised training methods struggle to accurately capture the true physics involved. Although physics-informed approaches provide some improvement, existing residual-based methods rely solely on local information and must be combined with standard supervised loss. In this work, we introduce Time Reversal Consistency (TRC), a novel physics-based training method that leverages the time reversibility of Maxwell's equations. TRC employs a time-reversed, differentiable finite-difference simulator to compare neural network predictions with a known initial condition. This approach offers both global physics guidance and supervision within a single function. We demonstrate that networks trained with TRC, using only randomized scatterers, generalize effectively to various arbitrarily structured media. We validate our method through the inverse design of a set of angle-to-angle couplers, addressing nearly two orders of magnitude more parameters than previous methods. Our findings indicate that the design quality achieved with TRC closely matches that of designs based on conventional simulators, while reducing design time by 95%. Materials Theory and Modeling Magnetics Materials and Devices Materials Engineering Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-4870131","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":336835497,"identity":"6ed6aae7-efe5-4aff-8f28-0cfe03d8b765","order_by":0,"name":"Shrija Nayanan","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Shrija","middleName":"","lastName":"Nayanan","suffix":""},{"id":336835498,"identity":"8bf13291-98e1-4941-b1ac-2288c125935b","order_by":1,"name":"Vikram Chopra","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Vikram","middleName":"","lastName":"Chopra","suffix":""},{"id":336835499,"identity":"36c72db1-ba5c-463f-8deb-9b2999b3bec5","order_by":2,"name":"Priya Sharma","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Priya","middleName":"","lastName":"Sharma","suffix":""},{"id":336835500,"identity":"8f819864-710a-48cb-b197-c84c29dccdd1","order_by":3,"name":"Aarav Patel","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8klEQVRIiWNgGAWjYNCCAgk5NvbmA0CWBQMDD2H1jA0MBjbGfDzHEhgYEiSI1pKWOE8ix4A4Lfyzm58/+GBwmLGNIefjY94fEnL8PAcYP3zMwa1F4s4xw8YZBoeZ2RjObjbmSZAwluxtYJacuQ2PNTcSDJt5DA6zsTH2bpMGaknccJ6BjZkXjxb5G+kfm/8YHOZhY+Z5RpwWgxs5hs1A70uwsfGwQbScbcCvxfDOmcKZPQY2BkAdxoZz0oB+6TnYjNcvcrfbN3z4USFRP3/+44cP3tjYAEMs+eCHj/i8L4EpBIwovACLllEwCkbBKBgFqAAAsjpM98uZZ+EAAAAASUVORK5CYII=","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Aarav","middleName":"","lastName":"Patel","suffix":""}],"badges":[],"createdAt":"2024-08-06 17:37:38","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-4870131/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4870131/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":61984883,"identity":"e0f22840-064a-41b5-a905-049c69f74667","added_by":"auto","created_at":"2024-08-08 00:24:32","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":147152,"visible":true,"origin":"","legend":"","description":"","filename":"NeuralElectromagneticSimulationTrainingwithTimereversalConsistency.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4870131/v1_covered_0db94550-d730-4320-a628-ff295099e194.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eNeural Electromagnetic Simulation Training with Time-reversal Consistency\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-4870131/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4870131/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eConventional electromagnetic wave simulators are characterized by lengthy simulation times, making them unsuitable for computational imaging and photonic inverse problems (such as end-to-end design and iterative reconstruction) that necessitate multiple evaluations of the forward model. Neural network-based electromagnetic wave simulators offer potential speed improvements by several orders of magnitude; however, traditional supervised training methods struggle to accurately capture the true physics involved. Although physics-informed approaches provide some improvement, existing residual-based methods rely solely on local information and must be combined with standard supervised loss. In this work, we introduce Time Reversal Consistency (TRC), a novel physics-based training method that leverages the time reversibility of Maxwell's equations. TRC employs a time-reversed, differentiable finite-difference simulator to compare neural network predictions with a known initial condition. This approach offers both global physics guidance and supervision within a single function. We demonstrate that networks trained with TRC, using only randomized scatterers, generalize effectively to various arbitrarily structured media. We validate our method through the inverse design of a set of angle-to-angle couplers, addressing nearly two orders of magnitude more parameters than previous methods. Our findings indicate that the design quality achieved with TRC closely matches that of designs based on conventional simulators, while reducing design time by 95%.\u003c/p\u003e","manuscriptTitle":"Neural Electromagnetic Simulation Training with Time-reversal Consistency","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-08-08 00:24:26","doi":"10.21203/rs.3.rs-4870131/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"33ca30f5-1f56-43ce-9290-5829c1ecce1b","owner":[],"postedDate":"August 8th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":35678791,"name":"Materials Theory and Modeling"},{"id":35678792,"name":"Magnetics Materials and Devices"},{"id":35678793,"name":"Materials Engineering"}],"tags":[],"updatedAt":"2024-08-08T00:24:26+00:00","versionOfRecord":[],"versionCreatedAt":"2024-08-08 00:24:26","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4870131","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4870131","identity":"rs-4870131","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}